# 32k Long Context

A fine-tuned version based on the Qwen3-30B-A3B Mixture of Experts model, increasing the number of active experts from 8 to 24, suitable for complex tasks requiring deep reasoning

Qwen3-4B-Base is the latest generation of the Qwen series with 4 billion parameters, supporting 32k context length and multilingual processing.

The latest generation large language model in the Qwen series, offering a 14.8 billion parameter pre-trained base model with support for 32k ultra-long context understanding

A 24B parameter model based on the Mistral architecture, distilled from the DeepSeek model, designed for speed and efficiency.

Mistral Small 3 (2501) is a large language model with 24 billion parameters, excelling in the small model category below 70B, supporting multilingual and advanced reasoning capabilities.

Qwen2-7B is a multilingual role-playing large language model that supports English, Korean, Japanese, Chinese, and Spanish, with a context length of 32k.

Mistral-7B-Instruct-v0.3 is a large language model based on Mistral-7B-v0.3 with instruction fine-tuning, supporting function calling and an expanded vocabulary.

Satoshi 7B is a large language model fine-tuned based on Bitcoin principles, Austrian economics, and libertarian principles, exhibiting strong Bitcoin maximalism and non-woke political biases.